Update app.py

app.py

@@ -3,20 +3,23 @@ os.environ['REPLICATE_API_TOKEN'] = "r8_afc5kESy4ucPojF3Tw1GE25ER4Ovudy1iPVw6"
 
 import replicate
 
-#Prompts 
+# Prompts
 pre_prompt = "You are a helpful assistant. You do not respond as 'User' or pretend to be 'User'. You only respond once as 'Assistant'."
-prompt_input = "What is streamlit"
+prompt_input = "What is Hugging Face"
 
-#Generate LLM response 
-output = replicate.run('a16z-infra/llama13b-v2-chat:df7690f1994d94e96ad9d568eac121aecf50684a0b0963b25a41cc40061269e5', #LLM model
-                       input={"prompt": f"{pre_prompt} {prompt_input} Assistant: ", #Prompts 
-                                  "temperature":0.1, "top_p":0.9, "max_length":124, "repetition_penalty":1}) #Model parameter 
-
- return output
+# Generate LLM response
+output = replicate.run('huggingface/llama-base-125M',  # LLM model
+                       input={
+                           "prompt": f"{pre_prompt} {prompt_input} Assistant: ",  # Prompts
+                           "temperature": 0.1,
+                           "top_p": 0.9,
+                           "max_length": 124,
+                           "repetition_penalty": 1
+                       })  # Model parameters
 
 full_response = ''
 
 for item in output:
- full_response += item
+    full_response += item
 
 print(full_response)